All Languages Matter: Opening Swahili-to-Sukuma on the Edge

In 2024 we built Kamusi, a way to learn, look up, and explore Swahili with AI nearby, and even then, the point was never Swahili alone. We believe all languages matter, and that intelligence should live in the languages people actually speak and write, not only the ones that already crowd the internet.

Sukuma is spoken by millions, and it should not wait at the edge of the map while tools keep arriving for everyone else. So today we open the next chapter: two Swahili → Sukuma translators, shared as a research preview and kept small on purpose so they can run on phones, everyday machines, and places where big cloud GPUs are scarce and the network is thin. Type Swahili below and you should see Sukuma (Kisukuma) come back.

Why two versions?

Not every device has the same room to spare, so we trained two sizes on the same kind of literary Swahili-Sukuma text. Reach for Quality when you can afford a stronger model, or Lite when memory and speed have to win. Both are on Hugging Face (quality · lite).

What to expect

This remains a research preview, and the direction is one-way: Swahili into Sukuma. The tone leans literary, so casual chat, legal wording, or medical phrasing may sound odd or off-register. Treat the box above as a living demo, and the open weights as a starting point for anyone who wants Sukuma in the loop rather than a finished product for every domain.

For builders

We trained on about 31,000 Swahili-Sukuma pairs and kept train and test apart by document so the check set would not leak the same stories. On that held-out evaluation, quality lands around chrF2 42.6 and lite around chrF2 34.8. If you load the weights yourself, force the Sukuma target tag (suk_Latn) with Swahili as source (swh_Latn). The try box already does that for you. The technical report below walks through training, metrics, and the limits we are still honest about.

Collaboration

If you are extending this work, evaluating on new data, or building with Sukuma in your community, write to us at hi@nileagi.com. The weights are released under CC BY-NC-SA 4.0; commercial use needs a written agreement with NileAGI.